Self organizing optimization and phase transition in reinforcement learning minority game system  

作　　者：Si-Ping Zhang Jia-Qi Dong Hui-Yu Zhang Yi-Xuan Lü Jue Wang Zi-Gang Huang 

机构地区：[1]Key Laboratory of Biomedical Information Engineering of Ministry of Education,Key Laboratory of Neuro-informatics&Rehabilitation Engineering of Ministry of Civil Affairs,and Institute of Health and Rehabilitation Science,School of Life Science and Technology,Xi’an Jiaotong University,Xi’an 710049,China [2]Lanzhou Center for Theoretical Physics and Key Laboratory of Theoretical Physics of Gansu Province,Lanzhou University,Lanzhou 730000,China

出　　处：《Frontiers of physics》2024年第4期297-309,共13页物理学前沿（英文版）

基　　金：This work was supported by the National Natural Science Foundation of China(Grant No.12105213);China Postdoctoral Science Foundation(No.2020M673363);the Natural Science Basic Research Program of Shaanxi(No.2021JQ-007).

摘　　要：Whether the complex game system composed of a large number of artificial intelligence(AI)agents empowered with reinforcement learning can produce extremely favorable collective behaviors just through the way of agent self-exploration is a matter of practical importance.In this paper,we address this question by combining the typical theoretical model of resource allocation system,the minority game model,with reinforcement learning.Each individual participating in the game is set to have a certain degree of intelligence based on reinforcement learning algorithm.In particular,we demonstrate that as AI agents gradually becomes familiar with the unknown environment and tries to provide optimal actions to maximize payoff,the whole system continues to approach the optimal state under certain parameter combinations,herding is effectively suppressed by an oscillating collective behavior which is a self-organizing pattern without any external interference.An interesting phenomenon is that a first-order phase transition is revealed based on some numerical results in our multi-agents system with reinforcement learning.In order to further understand the dynamic behavior of agent learning,we define and analyze the conversion path of belief mode,and find that the self-organizing condensation of belief modes appeared for the given trial and error rates in the AI system.Finally,we provide a detection method for period-two oscillation collective pattern emergence based on the Kullback–Leibler divergence and give the parameter position where the period-two appears.

关 键 词：oscillatory evolution collective behaviors phase transition reinforcement learning minority game 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]